Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4644 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.9805. Min Act: -0.1700
Data Index: 8094879 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.9805. Min Act: -0.1700
Data Index: 3314783 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.9805. Min Act: -0.1700
Data Index: 2857548 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.9180. Min Act: -0.1700
Data Index: 8128671 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.8867. Min Act: -0.1700
Data Index: 1087331 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.8555. Min Act: -0.1700
Data Index: 7110267 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.8242. Min Act: -0.1700
Data Index: 5809311 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7616. Min Act: -0.1700
Data Index: 3085211 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7929. Min Act: -0.1700
Data Index: 8080811 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7929. Min Act: -0.1700
Data Index: 5175226 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7929. Min Act: -0.1700
Data Index: 626451 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.8242. Min Act: -0.1700
Data Index: 717918 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7929. Min Act: -0.1700
Data Index: 1888847 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7616. Min Act: -0.1700
Data Index: 6144338 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7616. Min Act: -0.1700
Data Index: 4046959 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7616. Min Act: -0.1700
Data Index: 7110266 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7616. Min Act: -0.1700
Data Index: 3683687 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7616. Min Act: -0.1700
Data Index: 5934035 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7616. Min Act: -0.1700
Data Index: 3890458 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9805. Min Range: -3.9805
Max Act: 3.7304. Min Act: -0.1700
Data Index: 3811741 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19